Supercomputers/Systems/Otus
Germany · operational · mixed
Otus
Operated by Paderborn PC2 .
Phase 1 seed dataset, compiled by hand. These rows were built from public operator, laboratory and vendor sources. A mechanical second-reader pass has since fetched every cited source: 1092 of 1153 systems have a readable citation that names them, and 40 are genuinely weakly sourced. Every claim carries its source and a confidence tier. Treat anything below verified as a lead, not a citation.
Measured performance
- Rmax
- 4.66 PFlop/s
- Rpeak
- 7.45 PFlop/s
- Rmax ÷ Rpeak
- 62.6%
- Cores
- 19,440
- Power
- 68.18 kW
- Per watt
- 68.3 GF/W
Figures are as last publicly reported for the configuration described below, not a live measurement. Where a system was upgraded in place, the post-upgrade configuration is shown and the earlier one appears in the timeline.
What this machine is made of
One row per supplier relationship. “Supplier at build” is the company that shipped the part at the time; where that company has since been acquired, the parent it rolls up to today is shown beside it. That distinction is what makes ticker-level aggregation possible across a thirty-year dataset.
| Role | Part | Supplier at build | Quantity | Confidence | Source |
|---|---|---|---|---|---|
| Integrator | - Lenovo ThinkSystem SD665-N V3, installed by pro-com Datensysteme | Lenovo | - | Reported | top500.orgpc2.uni-paderborn.de |
| Accelerator | NVIDIA H100 SXM5 Accelerators CUDA (Hopper GH100) · 16,896C · 1.98 GHz · TSMC 4N · 700 W 108 NVIDIA H100 GPUs in 27 GPU nodes (TOP500 lists the 80GB SXM5 variant, PC2 states 94GB) | NVIDIA | 108 reported | Reported | pc2.uni-paderborn.detop500.org |
| CPU | - AMD EPYC 9655 96C 2.6GHz (Turin), dual-socket nodes | AMD | - | Reported | top500.orgpc2.uni-paderborn.de |
| Interconnect | NVIDIA InfiniBand NDR (Quantum-2) Interconnect Fat tree or dragonfly+ · 400 Gb/s per port · Under 0.6 microseconds Nvidia NDR InfiniBand fabric, 2:1 blocking factor | NVIDIA | - | Reported | pc2.uni-paderborn.detop500.org |
| Storage | - 5.4 PB on IBM Storage Scale | IBM | - | Reported | pc2.uni-paderborn.de |
| Operating system | - Rocky Linux 9.4 | Rocky Enterprise Software Foundation | - | Reported | top500.org |
The read
Paderborn University's PC2 flagship, a Lenovo ThinkSystem system installed by pro-com Datensysteme and put into operation on 10 November 2025 as an NHR machine with roughly twice the capacity of Noctua 2. The Rmax, Rpeak, core and power figures here are for TOP500's separate GPU-only entry (H100 SXM5, 19,440 cores, ranked 255th in June 2025), which placed fifth on the June 2025 Green500 at about 68.4 GFlops/Watt; the power figure is read from the Green500 list page. PC2 describes the whole system as 142,656 cores and 108 GPUs: 636 standard and 48 large-memory nodes with dual AMD EPYC 9655, 27 GPU nodes with four H100 94GB each, 32 accelerator nodes for FPGAs and GPUs, 5.4 PB on IBM Storage Scale and a 2:1 blocking NDR InfiniBand fabric. TOP500 names the GPU as the 80GB SXM5 variant where PC2 says 94GB.
Timeline
Public list appearances
Pointers only: rank and edition, linking to the canonical entry. We do not reproduce list tables. See sourcing policy.
Change history
- 2026-10-02 Added Otus, Paderborn's PC2 H100 system, 5th on the June 2025 Green500
Source check
We fetched this system's own citations and recorded whether each page actually mentions it. This is a corroboration signal, not a fact check, and it is published so you can see how well the sourcing holds up rather than take it on trust.
| Cited source | Result | Found on the page |
|---|---|---|
| pc2.uni-paderborn.de | names system, part and count | NVIDIA H100 SXM5, NVIDIA InfiniBand NDR (Quantum-2) · counts: 108 |
| top500.org | names system and part | NVIDIA H100 SXM5, NVIDIA InfiniBand NDR (Quantum-2) |
Checked 2026-10-09 by pnpm verify. Re-run it and the table changes with the web.
Further reading
Operating a supercomputer
Acceptance testing, why "installed" and "in production" are six months apart, and the machine lifecycle.
Inside a node
Latency-optimised versus throughput-optimised processors, NUMA, and the end of the host-to-device copy.
The interconnect
Topologies, why latency and tail behaviour matter more than bandwidth, and how the fabric market consolidated.